Dev now clears a week of Codex and Claude output in about a day: 'honestly a little scary'
jacob_posel · x · 2026-09-10
- A developer says he now gets through a full week's worth of Codex and Claude coding plans in about a day each, noting agent output has outpaced his own review bandwidth.
- He adds he doesn't even have time to use the tools more aggressively due to meetings — "honestly a little scary." A firsthand signal that AI coding throughput is outstripping human review capacity.
More from coding & agent
- AutoResearchExam uses hidden test sets to study how AI agents do 24-hour research — AlexGDimakis · 2026-09-10
- OpenAI DevDay Exchange announces 8-city tour starting October 16 in Bengaluru — OpenAIDevs · 2026-09-10
- Coinbase for Agents launches on Grok with no MCP setup required — MurrLincoln · 2026-09-10
- Databricks introduces Adaptive Instructed-Retriever for enterprise data agents — matei_zaharia · 2026-09-10
- Before coding an agent harness: charter, blueprint, threat model, then build — Telos_in_the_Void · 2026-09-10
- Coinbase for Agents lands on Grok: trade and automate crypto workflows with no MCP setup — kleffew94 · 2026-09-10